Hepatocellular Carcinoma (HCC)
Conditions
Keywords
Artificial Intelligence, Risk-Adapted Surveillance, Recurrence Surveillance, Early Detection of Recurrence, Clinical Decision Support, Liver Resection, Radiofrequency Ablation
Brief summary
Hepatocellular carcinoma, the most common type of primary liver cancer, can recur after liver resection or thermal ablation performed with curative intent. Follow-up imaging is commonly scheduled at fixed intervals, although the risk of recurrence differs among patients and may change over time. This study will test whether a locked artificial intelligence system can use routinely collected clinical, laboratory, and imaging information to recommend when the next surveillance scan should occur. Adults with no radiological evidence of viable hepatocellular carcinoma after microscopically margin-negative liver resection or complete radiofrequency or microwave ablation will be randomly assigned in a 1:1 ratio to artificial intelligence-guided risk-adapted surveillance or fixed-interval surveillance. In the artificial intelligence-guided group, participants classified as having high, intermediate, or low current recurrence risk will generally undergo the next protocol-scheduled contrast-enhanced imaging examination after 3, 4, or 6 months, respectively. Participants in the control group will undergo protocol-scheduled imaging every 4 months. The risk thresholds are designed so that the expected total number of protocol-scheduled imaging examinations is approximately comparable between the two groups over 24 months. The artificial intelligence system provides surveillance recommendations only. It does not diagnose recurrence, determine eligibility for liver transplantation, or select anticancer treatment. Clinically indicated examinations may be performed at any time in either group. When recurrence is confirmed, participants in both groups will undergo the same protocol-defined multidisciplinary evaluation, and potentially curative-intent treatment may be considered when clinically appropriate. The primary purpose is to determine whether artificial intelligence-guided surveillance increases the probability of being alive at 24 months without having a recurrence that is no longer amenable to protocol-defined curative-intent treatment. The study evaluates the timing and allocation of surveillance rather than an adjuvant anticancer treatment and is not intended to prevent the biological occurrence of recurrence.
Detailed description
Recurrence is common after curative-intent treatment of hepatocellular carcinoma. Surveillance after liver resection or thermal ablation is therefore an essential component of long-term care. However, conventional surveillance commonly applies similar imaging intervals to patients whose recurrence risks differ substantially and may change over time. A risk-adapted strategy could allocate surveillance examinations to periods when timely detection is most likely to preserve an opportunity for curative-intent management, while avoiding unnecessary examinations during lower-risk periods. This is a pragmatic, multicenter, open-label, parallel-group, patient-level randomized superiority trial with blinded central outcome assessment. Eligible participants will have undergone curative-intent microscopically margin-negative (R0) liver resection or complete radiofrequency or microwave ablation for hepatocellular carcinoma. Before randomization, protocol-specified contrast-enhanced computed tomography or magnetic resonance imaging must demonstrate no viable residual tumor. Complete response after thermal ablation will be established radiologically; absence of viable enhancement is not considered evidence that microscopic disease is absent. Participants will be randomly assigned in a 1:1 ratio to an artificial intelligence-guided risk-adapted surveillance strategy or a fixed-interval surveillance strategy. Randomization will be implemented centrally and stratified by study center and initial curative-intent treatment modality. Participants and treating clinicians cannot be masked to surveillance timing. Independent central reviewers and the committee adjudicating the primary outcome will remain unaware of randomized assignment. In the artificial intelligence-guided group, a locked artificial intelligence system will use protocol-defined baseline and longitudinal clinical, laboratory, and imaging information to estimate the participant's current risk of recurrence. Separate modality-specific components will be used for participants treated by resection and those treated by thermal ablation. Resection-specific pathological information will not be assumed to be available for participants treated by ablation. At each protocol-defined reassessment, participants classified as having high, intermediate, or low current risk will generally have their next protocol-scheduled contrast-enhanced imaging examination arranged after 3, 4, or 6 months, respectively. Prespecified changes in clinical status, tumor-marker trajectories, or other protocol-defined findings may trigger expedited diagnostic evaluation. Symptoms or clinically concerning findings must be evaluated irrespective of the artificial intelligence score or scheduled interval. Artificial intelligence outputs are advisory and may be overridden by the treating clinician for documented clinical reasons. Participants assigned to the control group will undergo contrast-enhanced surveillance imaging every 4 months according to a fixed protocol-defined schedule. The artificial intelligence thresholds and interval-mapping rules will be calibrated before enrollment so that the expected aggregate number of protocol-scheduled cross-sectional imaging examinations through Month 24 is approximately comparable between study groups. This resource-matching objective applies at the study-group level and does not mean that each participant will undergo the same number of examinations. All protocol-scheduled and unscheduled imaging examinations, false-positive investigations, radiation and contrast exposure, and related health-care use will be recorded. Except for the timing of protocol-scheduled surveillance imaging, procedures for evaluating suspected recurrence and access to recurrence management will be harmonized between the two groups. A positive artificial intelligence output or abnormal tumor-marker result will not by itself establish recurrence. Suspected recurrence will require guideline-concordant imaging and, when clinically indicated, pathological confirmation. After recurrence is confirmed, the treating multidisciplinary team will assess management using the same protocol-defined criteria in both groups. Potentially curative-intent options may include repeat liver resection, thermal ablation, or liver transplantation in appropriately selected patients. These treatments are not assigned or guaranteed by the artificial intelligence system or by the trial. Eligibility depends on recurrence extent, liver function, performance status, technical feasibility, patient preference, institutional capability, and applicable organ-allocation policies. Participants for whom curative-intent treatment is not appropriate may receive other guideline-concordant locoregional or systemic treatment. Treatment of underlying liver disease, including antiviral therapy when indicated, will continue according to the same clinical standards in both groups. Before enrollment of the first participant, the artificial intelligence model parameters, input variables, variable definitions, preprocessing procedures, handling of missing inputs, modality-specific components, risk thresholds, surveillance-interval mapping, output format, and software version will be finalized and locked. The deployed version will be documented using version identifiers, timestamps, and a reproducible code or model hash. Trial outcomes will not be used to retrain, recalibrate, or otherwise modify the model during the primary trial period. System inputs, outputs, recommended intervals, clinician overrides, scheduled examinations, and subsequent software changes will be recorded in audit logs. The principal clinical endpoint is curative-strategy failure-free survival through Month 24. A primary endpoint event is the first occurrence of recurrent hepatocellular carcinoma that a blinded independent central multidisciplinary adjudication committee determines is not amenable to protocol-defined curative-intent treatment, or death from any cause, whichever occurs first. A recurrence adjudicated as amenable to a protocol-defined curative-intent strategy is not considered a primary endpoint event at that time, and the participant will remain under follow-up. Secondary assessments will characterize the occurrence and timing of any recurrence, tumor burden and stage at recurrence, eligibility for and receipt of curative-intent salvage treatment, outcomes following salvage treatment, overall survival, conventional recurrence-free survival, surveillance burden, unscheduled diagnostic procedures, false-positive investigations, safety, health-related quality of life, adherence, and health-care resource use. Conventional recurrence-free survival is not the primary endpoint because different surveillance intervals can change the recorded time of recurrence detection without changing the biological time at which recurrence develops. The primary analysis will follow the intention-to-treat principle according to randomized assignment. Prespecified analyses will account for study center, initial treatment modality, missing data, adherence, clinician overrides, and heterogeneity across clinically relevant subgroups. Trial conduct, data quality, participant safety, and the occurrence of non-curatively treatable recurrence will be centrally monitored in accordance with the protocol and statistical analysis plan.
Interventions
OTHERArtificial Intelligence-Guided Risk-Adapted Surveillance
A locked artificial intelligence clinical decision-support system will estimate current recurrence risk from protocol-defined baseline and longitudinal information. Modality-specific model components will be used after liver resection and thermal ablation. Prespecified risk thresholds will map high, intermediate, and low current risk to the next protocol-scheduled contrast-enhanced imaging examination at 3, 4, or 6 months, respectively. The thresholds are calibrated so that the expected aggregate number of protocol-scheduled imaging examinations through Month 24 is approximately comparable with the control strategy. The system does not independently diagnose recurrence or prescribe treatment. Model inputs, outputs, recommendations, clinician overrides, and software versions will be recorded.
OTHERFixed-Interval Surveillance
Participants will undergo contrast-enhanced computed tomography or magnetic resonance imaging every 4 months through Month 24 according to a fixed protocol-defined surveillance schedule. Artificial intelligence risk estimates will not be provided. Unscheduled diagnostic assessment remains permitted when clinically indicated.
Sponsors
Tongji Hospital
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
HEALTH_SERVICES_RESEARCH
Masking
SINGLE (Outcomes Assessor)
Masking description
Participants and treating clinicians cannot be masked because the surveillance intervals differ between groups. Radiologists performing independent central imaging review and members of the central multidisciplinary committee adjudicating recurrence and eligibility for protocol-defined curative-intent treatment will remain unaware of randomized assignment. Group identifiers will be concealed in materials provided for central outcome adjudication.
Intervention model description
Participants will be randomized individually in a 1:1 ratio to a locked artificial intelligence-guided risk-adapted surveillance strategy or a fixed-interval surveillance strategy. Randomization will be implemented centrally and stratified by study center and initial curative-intent treatment modality, defined as microscopically margin-negative liver resection versus radiofrequency or microwave ablation. Participants will remain in their assigned surveillance strategy throughout the 24-month primary trial period. Both groups will use the same procedures for confirming suspected recurrence and the same multidisciplinary recurrence-management pathway; the principal difference between groups will be the timing of protocol-scheduled surveillance imaging.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Age 18 years or older at the time of informed consent. * First diagnosis of hepatocellular carcinoma, confirmed by histopathology for participants undergoing liver resection, or by histopathology or accepted guideline-concordant imaging criteria for participants undergoing thermal ablation. * Completion of first curative-intent treatment consisting of either R0 liver resection with microscopically tumor-negative margins or complete radiofrequency or microwave ablation of all known hepatocellular carcinoma. * Qualifying multiphasic contrast-enhanced CT or MRI obtained 28 to 56 days after completion of the final curative-intent procedure. * Qualifying imaging confirming no viable tumor at the resection bed or ablation site, no new intrahepatic hepatocellular carcinoma, and no macrovascular invasion, regional nodal disease, or extrahepatic metastasis. * No unresolved lesion requiring immediate diagnostic evaluation or treatment at the time of randomization. * Randomization within 14 days after the qualifying post-treatment imaging assessment and before the first protocol-scheduled surveillance examination. * Eastern Cooperative Oncology Group performance status of 0 or 1. * Child-Pugh class A liver function. * Medically fit for at least one protocol-defined curative-intent salvage treatment should an anatomically amenable recurrence be detected. * Able to undergo repeated protocol-required multiphasic contrast-enhanced CT or MRI examinations. * Availability of the minimum mandatory baseline data elements required to generate an output from the locked artificial intelligence system. * Able and willing to comply with trial procedures and provide written informed consent.
Exclusion criteria
* Any previous episode of hepatocellular carcinoma or previous hepatocellular carcinoma-directed treatment before the current index diagnosis. * Microscopically or macroscopically positive surgical margins (R1 or R2 resection). * Residual viable tumor after thermal ablation. * Any radiological evidence of residual, recurrent, nodal, or metastatic hepatocellular carcinoma at screening. * Macrovascular invasion, regional lymph-node metastasis, or extrahepatic metastasis associated with the index hepatocellular carcinoma. * Index treatment involving liver transplantation, combined resection and ablation, transarterial therapy, radiotherapy, systemic anticancer therapy, or another hepatocellular carcinoma-directed treatment other than the qualifying R0 resection or complete radiofrequency or microwave ablation. * Previous liver transplantation, active placement on a liver-transplant waiting list, or planned liver transplantation in the absence of documented recurrent hepatocellular carcinoma. * Planned or ongoing adjuvant antineoplastic treatment intended to reduce hepatocellular carcinoma recurrence after the qualifying procedure. Guideline-concordant antiviral treatment and management of the underlying liver disease are permitted. * Concurrent participation in another interventional study expected to affect hepatocellular carcinoma recurrence, survival, surveillance intensity, or eligibility for curative-intent salvage treatment. * Combined hepatocellular-cholangiocarcinoma or another non-hepatocellular primary hepatic malignancy. * A permanent medical contraindication that would preclude all protocol-defined curative-intent salvage treatment options. * Inability to undergo any protocol-permitted contrast-enhanced CT or MRI modality because of contraindication to all available imaging and contrast options. * Active malignancy other than hepatocellular carcinoma that requires anticancer treatment or is expected to materially interfere with survival, surveillance adherence, or outcome assessment during the primary 24-month follow-up period. * Uncontrolled hepatic decompensation, including refractory ascites or clinically significant hepatic encephalopathy. * Pregnancy at the time of randomization. * Inability or unwillingness to provide informed consent or comply with protocol-specified follow-up.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Curative-Strategy Failure-Free Survival at 24 Months | From randomization through Month 24 | Time from randomization to the first occurrence of recurrent hepatocellular carcinoma that a blinded independent central multidisciplinary adjudication committee determines is not amenable to protocol-defined curative-intent liver resection, thermal ablation, or liver transplantation, or death from any cause, whichever occurs first. A recurrence adjudicated as amenable to a protocol-defined curative-intent strategy is not considered an event at that time, and the participant remains under follow-up. The reported metric will be the estimated probability of remaining event-free at Month 24. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Overall Survival | From randomization through Month 36 | Overall survival is defined as the time from randomization to death from any cause. Participants who are alive at the data cutoff or whose vital status cannot be confirmed will be censored at the date they were last known to be alive. Vital status will be ascertained using harmonized follow-up procedures in both study groups. |
| Conventional Recurrence-Free Survival | From randomization through Month 36 | Recurrence-free survival is defined as the time from randomization to the first confirmed recurrence of hepatocellular carcinoma or death from any cause, whichever occurs first. Recurrence will be determined using protocol-defined imaging and, when clinically indicated, pathological criteria, with blinded independent central review. Participants without recurrence or death will be censored at the date of their last adequate disease assessment. |
| Curative-Intent Treatment Eligibility at First Recurrence | At the first confirmed recurrence occurring from randomization through Month 24 | The proportion of participants with a confirmed first recurrence whose recurrence is adjudicated by a blinded independent central multidisciplinary committee as amenable to at least one protocol-defined curative-intent treatment option, including liver resection, thermal ablation, or liver transplantation. Eligibility will be determined using prespecified clinical and technical criteria and will be assessed independently of whether the treatment is ultimately delivered. |
| Receipt of Curative-Intent Salvage Treatment | From confirmation of first recurrence through 12 months after recurrence, for recurrences occurring through Month 24 | The proportion of participants with a confirmed first recurrence who receive at least one protocol-defined curative-intent salvage treatment, including repeat liver resection, thermal ablation, or liver transplantation. Treatment receipt and curative intent will be documented prospectively. For a prespecified staged curative-intent strategy, the participant will be counted as having received treatment when the first protocol-defined component is initiated. |
| Complete Response After Curative-Intent Salvage | Within 12 weeks after completion of the first curative-intent salvage treatment | The proportion of participants who receive protocol-defined curative-intent salvage treatment and achieve complete radiological response, defined as no evidence of viable hepatocellular carcinoma, according to blinded independent central review using protocol-defined imaging criteria. |
| Early-Stage Disease at First Recurrence | At the first confirmed recurrence occurring from randomization through Month 24 | The proportion of participants with a confirmed first recurrence that is classified as Barcelona Clinic Liver Cancer stage 0 or A by blinded independent central review at the time recurrence is confirmed. The denominator will include all participants with a confirmed first recurrence during the specified assessment period. |
| Number of Protocol-Scheduled Cross-Sectional Imaging Examinations | From randomization through Month 24 | The cumulative number of protocol-scheduled contrast-enhanced computed tomography or magnetic resonance imaging examinations completed by each participant. This measure will assess whether the expected aggregate imaging burden is approximately comparable between the two surveillance strategies. |
| Total Number of Cross-Sectional Imaging Examinations | From randomization through Month 24 | The cumulative number of all contrast-enhanced computed tomography or magnetic resonance imaging examinations completed by each participant, including protocol-scheduled examinations and unscheduled examinations performed because of symptoms, abnormal laboratory findings, indeterminate imaging findings, or other clinical concerns. |
| False-Positive Surveillance Evaluations | From randomization through Month 24, including a 90-day confirmation window | The proportion of participants with at least one surveillance finding that leads to additional unplanned imaging, biopsy, or another diagnostic procedure but is not followed by confirmation of hepatocellular carcinoma recurrence within 90 days and is adjudicated by independent central review as not representing recurrence. |
| Change in EORTC QLQ-C30 Global Health Status and Quality of Life Score | At baseline and Months 6, 12, 18, and 24 | Change from baseline in the Global Health Status and Quality of Life score of the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire Core 30. Scores are transformed to a 0-to-100 scale, with higher scores indicating better overall health status and quality of life. The principal comparison will evaluate change from baseline to Month 24. |
| Surveillance-Related Serious Adverse Events | From randomization through Month 24 | The number and proportion of participants experiencing at least one serious adverse event considered related to protocol-scheduled or unscheduled surveillance imaging or associated diagnostic procedures. Seriousness and relatedness will be determined according to protocol-defined criteria and reviewed through the trial safety-monitoring process. |
Countries
China
Contacts
CONTACTZhao Huang, M.D
STUDY_DIRECTORZhao Huang
Tongji Hospital
Outcome results
None listed